© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130925
    Prev
    Next
    INDEX
    Explanations

    rewards and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [
    -0.06
     göster
    -0.06
     [.
    -0.06
    dimensions
    -0.05
     verbo
    -0.05
    ঠিক
    -0.05
    itty
    -0.05
     Chou
    -0.05
     deri
    -0.05
    Until
    -0.05
    POSITIVE LOGITS
     rewards
    0.08
     reward
    0.07
    வதால்
    0.07
     большого
    0.07
    奖励
    0.07
     récomp
    0.07
    只限
    0.06
     Rewards
    0.06
     zorgen
    0.06
    rewards
    0.06
    Activations Density 0.002%

    No Known Activations